360 安全技能中心

MH openai-whisper

通过 whisper 命令行工具在本地进行语音转文字：可指定模型大小、输出 txt/srt 等格式，也可用 translate 任务翻译为英文；首次运行时模型会下载到本地缓存目录，全程不需要 API key。

mohdalhashemi98-hue

热度 76.06

最近更新 2026-05-11 17:27:12

分类：效率依赖：读写文件应用场景：文件转换 / 翻译

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add mh-openai-whisper

Metadata

name: openai-whisper
description: Local speech-to-text with the Whisper CLI (no API key).
homepage: https://openai.com/research/whisper
metadata: {"openclaw":{"emoji":"🎙️","requires":{"bins":["whisper"]},"install":[{"id":"brew","kind":"brew","formula":"openai-whisper","bins":["whisper"],"label":"Install OpenAI Whisper (brew)"}]}}

Whisper (CLI)

Use whisper to transcribe audio locally.

Quick start

whisper /path/audio.mp3 --model medium --output_format txt --output_dir .
whisper /path/audio.m4a --task translate --output_format srt

Notes

Models download to ~/.cache/whisper on first run.
--model defaults to turbo on this install.
Use smaller models for speed, larger for accuracy.